Publications

@misc{kwon_evaluating_2025,

title = {Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans},

author = {Deuksin Kwon and Kaleen Shrestha and Bin Han and Elena Hayoung Lee and Gale Lucas},

url = {http://arxiv.org/abs/2509.16394},

doi = {10.48550/arXiv.2509.16394},

year  = {2025},

date = {2025-09-01},

urldate = {2025-09-25},

publisher = {arXiv},

abstract = {Large Language Models (LLMs) are increasingly deployed in socially complex, interaction-driven tasks, yet their ability to mirror human behavior in emotionally and strategically complex contexts remains underexplored. This study assesses the behavioral alignment of personality-prompted LLMs in adversarial dispute resolution by simulating multi-turn conflict dialogues that incorporate negotiation. Each LLM is guided by a matched Five-Factor personality profile to control for individual variation and enhance realism. We evaluate alignment across three dimensions: linguistic style, emotional expression (e.g., anger dynamics), and strategic behavior. GPT-4.1 achieves the closest alignment with humans in linguistic style and emotional dynamics, while Claude-3.7-Sonnet best reflects strategic behavior. Nonetheless, substantial alignment gaps persist. Our findings establish a benchmark for alignment between LLMs and humans in socially complex interactions, underscoring both the promise and the limitations of personality conditioning in dialogue modeling.},

note = {arXiv:2509.16394 [cs]},

keywords = {AI, DTIC, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{wang_implicit_2025,

title = {Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations},

author = {Yunzhe Wang and Gale M. Lucas and Burcin Becerik-Gerber and Volkan Ustun},

url = {http://arxiv.org/abs/2509.16457},

doi = {10.48550/arXiv.2509.16457},

year  = {2025},

date = {2025-09-01},

urldate = {2025-09-25},

publisher = {arXiv},

abstract = {Language-driven generative agents have enabled large-scale social simulations with transformative uses, from interpersonal training to aiding global policy-making. However, recent studies indicate that generative agent behaviors often deviate from expert expectations and real-world data–a phenomenon we term the Behavior-Realism Gap. To address this, we introduce a theoretical framework called Persona-Environment Behavioral Alignment (PEBA), formulated as a distribution matching problem grounded in Lewin's behavior equation stating that behavior is a function of the person and their environment. Leveraging PEBA, we propose PersonaEvolve (PEvo), an LLM-based optimization algorithm that iteratively refines agent personas, implicitly aligning their collective behaviors with realistic expert benchmarks within a specified environmental context. We validate PEvo in an active shooter incident simulation we developed, achieving an 84% average reduction in distributional divergence compared to no steering and a 34% improvement over explicit instruction baselines. Results also show PEvo-refined personas generalize to novel, related simulation scenarios. Our method greatly enhances behavioral realism and reliability in high-stakes social simulations. More broadly, the PEBA-PEvo framework provides a principled approach to developing trustworthy LLM-driven social simulations.},

note = {arXiv:2509.16457 [cs]},

keywords = {AI, DTIC, Virtual Agents},

pubstate = {published},

tppubtype = {misc}

}

@misc{wang_data-driven_2025,

title = {A data-driven discretized CS:GO simulation environment to facilitate strategic multi-agent planning research},

author = {Yunzhe Wang and Volkan Ustun and Chris McGroarty},

url = {http://arxiv.org/abs/2509.06355},

doi = {10.48550/arXiv.2509.06355},

year  = {2025},

date = {2025-09-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {Modern simulation environments for complex multi-agent interactions must balance high-fidelity detail with computational efficiency. We present DECOY, a novel multi-agent simulator that abstracts strategic, long-horizon planning in 3D terrains into high-level discretized simulation while preserving low-level environmental fidelity. Using Counter-Strike: Global Offensive (CS:GO) as a testbed, our framework accurately simulates gameplay using only movement decisions as tactical positioning – without explicitly modeling low-level mechanics such as aiming and shooting. Central to our approach is a waypoint system that simplifies and discretizes continuous states and actions, paired with neural predictive and generative models trained on real CS:GO tournament data to reconstruct event outcomes. Extensive evaluations show that replays generated from human data in DECOY closely match those observed in the original game. Our publicly available simulation environment provides a valuable tool for advancing research in strategic multi-agent planning and behavior generation.},

note = {arXiv:2509.06355 [cs]},

keywords = {DTIC, Simulation},

pubstate = {published},

tppubtype = {misc}

}

@misc{rakshit_emotionally-aware_2025,

title = {Emotionally-Aware Agents for Dispute Resolution},

author = {Sushrita Rakshit and James Hale and Kushal Chawla and Jeanne M. Brett and Jonathan Gratch},

url = {http://arxiv.org/abs/2509.04465},

doi = {10.48550/arXiv.2509.04465},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {In conflict, people use emotional expressions to shape their counterparts' thoughts, feelings, and actions. This paper explores whether automatic text emotion recognition offers insight into this influence in the context of dispute resolution. Prior work has shown the promise of such methods in negotiations; however, disputes evoke stronger emotions and different social processes. We use a large corpus of buyer-seller dispute dialogues to investigate how emotional expressions shape subjective and objective outcomes. We further demonstrate that large-language models yield considerably greater explanatory power than previous methods for emotion intensity annotation and better match the decisions of human annotators. Findings support existing theoretical models for how emotional expressions contribute to conflict escalation and resolution and suggest that agent-based systems could be useful in managing disputes by recognizing and potentially mitigating emotional escalation.},

note = {arXiv:2509.04465 [cs]},

keywords = {AI, DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{beltz_guarding_2025,

title = {Guarding Against Malicious Biased Threats (GAMBiT) Experiments: Revealing Cognitive Bias in Human-Subjects Red-Team Cyber Range Operations},

author = {Brandon Beltz and Jim Doty and Yvonne Fonken and Nikolos Gurney and Brett Israelsen and Nathan Lau and Stacy Marsella and Rachelle Thomas and Stoney Trent and Peggy Wu and Ya-Ting Yang and Quanyan Zhu},

url = {http://arxiv.org/abs/2508.20963},

doi = {10.48550/arXiv.2508.20963},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {We present three large-scale human-subjects red-team cyber range datasets from the Guarding Against Malicious Biased Threats (GAMBiT) project. Across Experiments 1-3 (July 2024-March 2025), 19-20 skilled attackers per experiment conducted two 8-hour days of self-paced operations in a simulated enterprise network (SimSpace Cyber Force Platform) while we captured multi-modal data: self-reports (background, demographics, psychometrics), operational notes, terminal histories, keylogs, network packet captures (PCAP), and NIDS alerts (Suricata). Each participant began from a standardized Kali Linux VM and pursued realistic objectives (e.g., target discovery and data exfiltration) under controlled constraints. Derivative curated logs and labels are included. The combined release supports research on attacker behavior modeling, bias-aware analytics, and method benchmarking. Data are available via IEEE Dataport entries for Experiments 1-3.},

note = {arXiv:2508.20963 [cs]},

keywords = {DTIC, Security},

pubstate = {published},

tppubtype = {misc}

}

@misc{chen_idu_2025,

title = {IDU: Incremental Dynamic Update of Existing 3D Virtual Environments with New Imagery Data},

author = {Meida Chen and Luis Leal and Yue Hu and Rong Liu and Butian Xiong and Andrew Feng and Jiuyi Xu and Yangming Shi},

url = {http://arxiv.org/abs/2508.17579},

doi = {10.48550/arXiv.2508.17579},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {For simulation and training purposes, military organizations have made substantial investments in developing high-resolution 3D virtual environments through extensive imaging and 3D scanning. However, the dynamic nature of battlefield conditions-where objects may appear or vanish over time-makes frequent full-scale updates both time-consuming and costly. In response, we introduce the Incremental Dynamic Update (IDU) pipeline, which efficiently updates existing 3D reconstructions, such as 3D Gaussian Splatting (3DGS), with only a small set of newly acquired images. Our approach starts with camera pose estimation to align new images with the existing 3D model, followed by change detection to pinpoint modifications in the scene. A 3D generative AI model is then used to create high-quality 3D assets of the new elements, which are seamlessly integrated into the existing 3D model. The IDU pipeline incorporates human guidance to ensure high accuracy in object identification and placement, with each update focusing on a single new object at a time. Experimental results confirm that our proposed IDU pipeline significantly reduces update time and labor, offering a cost-effective and targeted solution for maintaining up-to-date 3D models in rapidly evolving military scenarios.},

note = {arXiv:2508.17579 [cs]},

keywords = {DTIC, VGL},

pubstate = {published},

tppubtype = {misc}

}

@misc{hans_quantifying_2025,

title = {Quantifying Loss Aversion in Cyber Adversaries via LLM Analysis},

author = {Soham Hans and Nikolos Gurney and Stacy Marsella and Sofia Hirschmann},

url = {http://arxiv.org/abs/2508.13240},

doi = {10.48550/arXiv.2508.13240},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {Understanding and quantifying human cognitive biases from empirical data has long posed a formidable challenge, particularly in cybersecurity, where defending against unknown adversaries is paramount. Traditional cyber defense strategies have largely focused on fortification, while some approaches attempt to anticipate attacker strategies by mapping them to cognitive vulnerabilities, yet they fall short in dynamically interpreting attacks in progress. In recognition of this gap, IARPA's ReSCIND program seeks to infer, defend against, and even exploit attacker cognitive traits. In this paper, we present a novel methodology that leverages large language models (LLMs) to extract quantifiable insights into the cognitive bias of loss aversion from hacker behavior. Our data are collected from an experiment in which hackers were recruited to attack a controlled demonstration network. We process the hacker generated notes using LLMs using it to segment the various actions and correlate the actions to predefined persistence mechanisms used by hackers. By correlating the implementation of these mechanisms with various operational triggers, our analysis provides new insights into how loss aversion manifests in hacker decision-making. The results demonstrate that LLMs can effectively dissect and interpret nuanced behavioral patterns, thereby offering a transformative approach to enhancing cyber defense strategies through real-time, behavior-based analysis.},

note = {arXiv:2508.13240 [cs]},

keywords = {DTIC, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{chaubey_face-llava_2025,

title = {Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning},

author = {Ashutosh Chaubey and Xulang Guan and Mohammad Soleymani},

url = {https://arxiv.org/abs/2504.07198},

doi = {10.48550/ARXIV.2504.07198},

year  = {2025},

date = {2025-04-01},

urldate = {2025-04-15},

publisher = {arXiv},

abstract = {The human face plays a central role in social communication, necessitating the use of performant computer vision tools for human-centered applications. We propose Face-LLaVA, a multimodal large language model for face-centered, in-context learning, including facial expression and attribute recognition. Additionally, Face-LLaVA is able to generate natural language descriptions that can be used for reasoning. Leveraging existing visual databases, we first developed FaceInstruct-1M, a face-centered database for instruction tuning MLLMs for face processing. We then developed a novel face-specific visual encoder powered by Face-Region Guided Cross-Attention that integrates face geometry with local visual features. We evaluated the proposed method across nine different datasets and five different face processing tasks, including facial expression recognition, action unit detection, facial attribute detection, age estimation and deepfake detection. Face-LLaVA achieves superior results compared to existing open-source MLLMs and competitive performance compared to commercial solutions. Our model output also receives a higher reasoning rating by GPT under a zero-shot setting across all the tasks. Both our dataset and model wil be released at https://face-llava.github.io to support future advancements in social AI and foundational vision-language research.},

note = {Version Number: 1},

keywords = {DTIC, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{hale_kodis_2025,

title = {KODIS: A Multicultural Dispute Resolution Dialogue Corpus},

author = {James Hale and Sushrita Rakshit and Kushal Chawla and Jeanne M. Brett and Jonathan Gratch},

url = {http://arxiv.org/abs/2504.12723},

doi = {10.48550/arXiv.2504.12723},

year  = {2025},

date = {2025-04-01},

urldate = {2025-05-20},

publisher = {arXiv},

abstract = {We present KODIS, a dyadic dispute resolution corpus containing thousands of dialogues from over 75 countries. Motivated by a theoretical model of culture and conflict, participants engage in a typical customer service dispute designed by experts to evoke strong emotions and conflict. The corpus contains a rich set of dispositional, process, and outcome measures. The initial analysis supports theories of how anger expressions lead to escalatory spirals and highlights cultural differences in emotional expression. We make this corpus and data collection framework available to the community.},

note = {arXiv:2504.12723 [cs]},

keywords = {Dialogue, DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{siniukov_ditailistener_2025,

title = {DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion},

author = {Maksim Siniukov and Di Chang and Minh Tran and Hongkun Gong and Ashutosh Chaubey and Mohammad Soleymani},

url = {https://arxiv.org/abs/2504.04010},

doi = {10.48550/ARXIV.2504.04010},

year  = {2025},

date = {2025-03-01},

urldate = {2025-04-15},

publisher = {arXiv},

abstract = {Generating naturalistic and nuanced listener motions for extended interactions remains an open problem. Existing methods often rely on low-dimensional motion codes for facial behavior generation followed by photorealistic rendering, limiting both visual fidelity and expressive richness. To address these challenges, we introduce DiTaiListener, powered by a video diffusion model with multimodal conditions. Our approach first generates short segments of listener responses conditioned on the speaker's speech and facial motions with DiTaiListener-Gen. It then refines the transitional frames via DiTaiListener-Edit for a seamless transition. Specifically, DiTaiListener-Gen adapts a Diffusion Transformer (DiT) for the task of listener head portrait generation by introducing a Causal Temporal Multimodal Adapter (CTM-Adapter) to process speakers' auditory and visual cues. CTM-Adapter integrates speakers' input in a causal manner into the video generation process to ensure temporally coherent listener responses. For long-form video generation, we introduce DiTaiListener-Edit, a transition refinement video-to-video diffusion model. The model fuses video segments into smooth and continuous videos, ensuring temporal consistency in facial expressions and image quality when merging short video segments produced by DiTaiListener-Gen. Quantitatively, DiTaiListener achieves the state-of-the-art performance on benchmark datasets in both photorealism (+73.8% in FID on RealTalk) and motion representation (+6.1% in FD metric on VICO) spaces. User studies confirm the superior performance of DiTaiListener, with the model being the clear preference in terms of feedback, diversity, and smoothness, outperforming competitors by a significant margin.},

note = {Version Number: 1},

keywords = {DTIC, VGL},

pubstate = {published},

tppubtype = {misc}

}

@misc{ustun_abstracting_2025,

title = {Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning},

author = {Volkan Ustun and Soham Hans and Rajay Kumar and Yunzhe Wang},

url = {http://arxiv.org/abs/2503.20078},

doi = {10.48550/arXiv.2503.20078},

year  = {2025},

date = {2025-03-01},

urldate = {2025-04-15},

publisher = {arXiv},

abstract = {Multi-agent reinforcement learning (MARL) is increasingly ubiquitous in training dynamic and adaptive synthetic characters for interactive simulations on geo-specific terrains. Frameworks such as Unity's ML-Agents help to make such reinforcement learning experiments more accessible to the simulation community. Military training simulations also benefit from advances in MARL, but they have immense computational requirements due to their complex, continuous, stochastic, partially observable, non-stationary, and doctrine-based nature. Furthermore, these simulations require geo-specific terrains, further exacerbating the computational resources problem. In our research, we leverage Unity's waypoints to automatically generate multi-layered representation abstractions of the geo-specific terrains to scale up reinforcement learning while still allowing the transfer of learned policies between different representations. Our early exploratory results on a novel MARL scenario, where each side has differing objectives, indicate that waypoint-based navigation enables faster and more efficient learning while producing trajectories similar to those taken by expert human players in CSGO gaming environments. This research points out the potential of waypoint-based navigation for reducing the computational costs of developing and training MARL models for military training simulations, where geo-specific terrains and differing objectives are crucial.},

note = {arXiv:2503.20078 [cs]},

keywords = {DTIC, Simulation},

pubstate = {published},

tppubtype = {misc}

}

@misc{jalal-kamali_predicting_2025,

title = {Predicting Team Performance from Communications in Simulated Search-and-Rescue},

author = {Ali Jalal-Kamali and Nikolos Gurney and David Pynadath},

url = {http://arxiv.org/abs/2503.03791},

doi = {10.48550/arXiv.2503.03791},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-18},

publisher = {arXiv},

abstract = {Understanding how individual traits influence team performance is valuable, but these traits are not always directly observable. Prior research has inferred traits like trust from behavioral data. We analyze conversational data to identify team traits and their correlation with teaming outcomes. Using transcripts from a Minecraft-based search-and-rescue experiment, we apply topic modeling and clustering to uncover key interaction patterns. Our findings show that variations in teaming outcomes can be explained through these inferences, with different levels of predictive power derived from individual traits and team dynamics.},

note = {arXiv:2503.03791 [cs]},

keywords = {AI, DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{kwon_astra_2025,

title = {ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning through Action in Dynamic Offer Optimization},

author = {Deuksin Kwon and Jiwon Hae and Emma Clift and Daniel Shamsoddini and Jonathan Gratch and Gale M. Lucas},

url = {http://arxiv.org/abs/2503.07129},

doi = {10.48550/arXiv.2503.07129},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-18},

publisher = {arXiv},

abstract = {Negotiation requires dynamically balancing self-interest and cooperation to maximize one's own utility. Yet, existing agents struggle due to bounded rationality in human data, low adaptability to counterpart behavior, and limited strategic reasoning. To address this, we introduce principle-driven negotiation agents, powered by ASTRA, a novel framework for turn-level offer optimization grounded in two core principles: opponent modeling and Tit-for-Tat reciprocity. ASTRA operates in three stages: (1) interpreting counterpart behavior, (2) optimizing counteroffers via a linear programming (LP) solver, and (3) selecting offers based on negotiation tactics and the partner's acceptance probability. Through simulations and human evaluations, our agent effectively adapts to an opponent's shifting stance and achieves favorable outcomes through enhanced adaptability and strategic reasoning. Beyond improving negotiation performance, it also serves as a powerful coaching tool, offering interpretable strategic feedback and optimal offer recommendations.},

note = {arXiv:2503.07129 [cs]},

keywords = {DTIC, Virtual Agents},

pubstate = {published},

tppubtype = {misc}

}

@misc{liu_investigating_2025,

title = {Investigating Role of Personal Factors in Shaping Responses to Active Shooter Incident using Machine Learning},

author = {Ruying Liu and Burçin Becerik-Gerber and Gale M. Lucas},

url = {http://arxiv.org/abs/2503.05719},

doi = {10.48550/arXiv.2503.05719},

year  = {2025},

date = {2025-02-01},

urldate = {2025-03-18},

publisher = {arXiv},

abstract = {This study bridges the knowledge gap on how personal factors affect building occupants' responses in active shooter situations by applying interpretable machine learning methods to data from 107 participants. The personal factors studied are training methods, prior training experience, sense of direction, and gender. The response performance measurements consist of decisions (run, hide, multiple), vulnerability (corresponding to the time a participant is visible to a shooter), and pre-evacuation time. The results indicate that the propensity to run significantly determines overall response strategies, overshadowing vulnerability, and pre-evacuation time. The training method is a critical factor where VR-based training leads to better responses than video-based training. A better sense of direction and previous training experience are correlated with a greater propensity to run and less vulnerability. Gender slightly influences decisions and vulnerability but significantly impacts pre-evacuation time, with females evacuating slower, potentially due to higher risk perception. This study underscores the importance of personal factors in shaping responses to active shooter incidents.},

note = {arXiv:2503.05719 [cs]},

keywords = {DTIC, Social Simulation, VR},

pubstate = {published},

tppubtype = {misc}

}

@misc{tak_mechanistic_2025,

title = {Mechanistic Interpretability of Emotion Inference in Large Language Models},

author = {Ala N. Tak and Amin Banayeeanzade and Anahita Bolourani and Mina Kian and Robin Jia and Jonathan Gratch},

url = {http://arxiv.org/abs/2502.05489},

doi = {10.48550/arXiv.2502.05489},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-20},

publisher = {arXiv},

abstract = {Large language models (LLMs) show promising capabilities in predicting human emotions from text. However, the mechanisms through which these models process emotional stimuli remain largely unexplored. Our study addresses this gap by investigating how autoregressive LLMs infer emotions, showing that emotion representations are functionally localized to specific regions in the model. Our evaluation includes diverse model families and sizes and is supported by robustness checks. We then show that the identified representations are psychologically plausible by drawing on cognitive appraisal theory, a well-established psychological framework positing that emotions emerge from evaluations (appraisals) of environmental stimuli. By causally intervening on construed appraisal concepts, we steer the generation and show that the outputs align with theoretical and intuitive expectations. This work highlights a novel way to causally intervene and precisely shape emotional text generation, potentially benefiting safety and alignment in sensitive affective domains.},

note = {arXiv:2502.05489 [cs]},

keywords = {DTIC, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{walsh_fine-tuning_2025,

title = {Fine-tuning for Better Few Shot Prompting: An Empirical Comparison for Short Answer Grading},

author = {Joel Walsh and Siddarth Mamidanna and Benjamin Nye and Mark Core and Daniel Auerbach},

url = {https://arxiv.org/abs/2508.04063},

doi = {10.48550/ARXIV.2508.04063},

year  = {2025},

date = {2025-01-01},

urldate = {2025-08-19},

publisher = {arXiv},

abstract = {Research to improve Automated Short Answer Grading has recently focused on Large Language Models (LLMs) with prompt engineering and no- or few-shot prompting to achieve best results. This is in contrast to the fine-tuning approach, which has historically required large-scale compute clusters inaccessible to most users. New closed-model approaches such as OpenAI's fine-tuning service promise results with as few as 100 examples, while methods using open weights such as quantized low-rank adaptive (QLORA) can be used to fine-tune models on consumer GPUs. We evaluate both of these fine-tuning methods, measuring their interaction with few-shot prompting for automated short answer grading (ASAG) with structured (JSON) outputs. Our results show that finetuning with small amounts of data has limited utility for Llama open-weight models, but that fine-tuning methods can outperform few-shot baseline instruction-tuned LLMs for OpenAI's closed models. While our evaluation set is limited, we find some evidence that the observed benefits of finetuning may be impacted by the domain subject matter. Lastly, we observed dramatic improvement with the LLama 3.1 8B-Instruct open-weight model by seeding the initial training examples with a significant amount of cheaply generated synthetic training data.},

note = {Version Number: 1},

keywords = {DTIC, Machine Learning},

pubstate = {published},

tppubtype = {misc}

}

@misc{behzad_beyond_2025,

title = {Beyond Predictions: A Study of AI Strength and Weakness Transparency Communication on Human-AI Collaboration},

author = {Tina Behzad and Nikolos Gurney and Ning Wang and David V. Pynadath},

url = {https://arxiv.org/abs/2508.09033},

doi = {10.48550/ARXIV.2508.09033},

year  = {2025},

date = {2025-01-01},

urldate = {2025-08-19},

publisher = {arXiv},

abstract = {The promise of human-AI teaming lies in humans and AI working together to achieve performance levels neither could accomplish alone. Effective communication between AI and humans is crucial for teamwork, enabling users to efficiently benefit from AI assistance. This paper investigates how AI communication impacts human-AI team performance. We examine AI explanations that convey an awareness of its strengths and limitations. To achieve this, we train a decision tree on the model's mistakes, allowing it to recognize and explain where and why it might err. Through a user study on an income prediction task, we assess the impact of varying levels of information and explanations about AI predictions. Our results show that AI performance insights enhance task performance, and conveying AI awareness of its strengths and weaknesses improves trust calibration. These findings highlight the importance of considering how information delivery influences user trust and reliance in AI-assisted decision-making.},

note = {Version Number: 1},

keywords = {AI, DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{liu_deformable_2025,

title = {Deformable Beta Splatting},

author = {Rong Liu and Dylan Sun and Meida Chen and Yue Wang and Andrew Feng},

url = {http://arxiv.org/abs/2501.18630},

doi = {10.48550/arXiv.2501.18630},

year  = {2025},

date = {2025-01-01},

urldate = {2025-02-20},

publisher = {arXiv},

abstract = {3D Gaussian Splatting (3DGS) has advanced radiance field reconstruction by enabling real-time rendering. However, its reliance on Gaussian kernels for geometry and low-order Spherical Harmonics (SH) for color encoding limits its ability to capture complex geometries and diverse colors. We introduce Deformable Beta Splatting (DBS), a deformable and compact approach that enhances both geometry and color representation. DBS replaces Gaussian kernels with deformable Beta Kernels, which offer bounded support and adaptive frequency control to capture fine geometric details with higher fidelity while achieving better memory efficiency. In addition, we extended the Beta Kernel to color encoding, which facilitates improved representation of diffuse and specular components, yielding superior results compared to SH-based methods. Furthermore, Unlike prior densification techniques that depend on Gaussian properties, we mathematically prove that adjusting regularized opacity alone ensures distribution-preserved Markov chain Monte Carlo (MCMC), independent of the splatting kernel type. Experimental results demonstrate that DBS achieves state-of-the-art visual quality while utilizing only 45% of the parameters and rendering 1.5x faster than 3DGS-based methods. Notably, for the first time, splatting-based methods outperform state-of-the-art Neural Radiance Fields, highlighting the superior performance and efficiency of DBS for real-time radiance field rendering.},

note = {arXiv:2501.18630 [cs]},

keywords = {DTIC, Narrative},

pubstate = {published},

tppubtype = {misc}

}

@misc{chang_x-dyna_2025,

title = {X-Dyna: Expressive Dynamic Human Image Animation},

author = {Di Chang and Hongyi Xu and You Xie and Yipeng Gao and Zhengfei Kuang and Shengqu Cai and Chenxu Zhang and Guoxian Song and Chao Wang and Yichun Shi and Zeyuan Chen and Shijie Zhou and Linjie Luo and Gordon Wetzstein and Mohammad Soleymani},

url = {http://arxiv.org/abs/2501.10021},

doi = {10.48550/arXiv.2501.10021},

year  = {2025},

date = {2025-01-01},

urldate = {2025-02-20},

publisher = {arXiv},

abstract = {We introduce X-Dyna, a novel zero-shot, diffusion-based pipeline for animating a single human image using facial expressions and body movements derived from a driving video, that generates realistic, context-aware dynamics for both the subject and the surrounding environment. Building on prior approaches centered on human pose control, X-Dyna addresses key shortcomings causing the loss of dynamic details, enhancing the lifelike qualities of human video animations. At the core of our approach is the Dynamics-Adapter, a lightweight module that effectively integrates reference appearance context into the spatial attentions of the diffusion backbone while preserving the capacity of motion modules in synthesizing fluid and intricate dynamic details. Beyond body pose control, we connect a local control module with our model to capture identity-disentangled facial expressions, facilitating accurate expression transfer for enhanced realism in animated scenes. Together, these components form a unified framework capable of learning physical human motion and natural scene dynamics from a diverse blend of human and scene videos. Comprehensive qualitative and quantitative evaluations demonstrate that X-Dyna outperforms state-of-the-art methods, creating highly lifelike and expressive animations. The code is available at https://github.com/bytedance/X-Dyna.},

note = {arXiv:2501.10021 [cs]},

keywords = {DTIC, VGL},

pubstate = {published},

tppubtype = {misc}

}

@misc{siniukov_towards_2025,

title = {Towards a Generalizable Speech Marker for Parkinson's Disease Diagnosis},

author = {Maksim Siniukov and Ellie Xing and Sanaz and Attaripour Isfahani and Mohammad Soleymani},

url = {https://arxiv.org/abs/2501.03581},

doi = {10.48550/ARXIV.2501.03581},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-14},

publisher = {arXiv},

abstract = {Parkinson's Disease (PD) is a neurodegenerative disorder characterized by motor symptoms, including altered voice production in the early stages. Early diagnosis is crucial not only to improve PD patients' quality of life but also to enhance the efficacy of potential disease-modifying therapies during early neurodegeneration, a window often missed by current diagnostic tools. In this paper, we propose a more generalizable approach to PD recognition through domain adaptation and self-supervised learning. We demonstrate the generalization capabilities of the proposed approach across diverse datasets in different languages. Our approach leverages HuBERT, a large deep neural network originally trained for speech recognition and further trains it on unlabeled speech data from a population that is similar to the target group, i.e., the elderly, in a self-supervised manner. The model is then fine-tuned and adapted for use across different datasets in multiple languages, including English, Italian, and Spanish. Evaluations on four publicly available PD datasets demonstrate the model's efficacy, achieving an average specificity of 92.1% and an average sensitivity of 91.2%. This method offers objective and consistent evaluations across large populations, addressing the variability inherent in human assessments and providing a non-invasive, cost-effective and accessible diagnostic option.},

note = {Version Number: 1},

keywords = {DTIC},

pubstate = {published},

tppubtype = {misc}

}